neohaskell/docs/archive/2026-07-ai-artifacts/claude-skills/integration-pipeline-preview/02-classify-integration/02-persist
docs/archive/2026-07-ai-artifacts/claude-skills/integration-pipeline-preview/02-classify-integration/02-persist/SKILL.md
> **ARCHIVAL KNOWLEDGE — DO NOT USE OR REFERENCE.** > Superseded by `codemap/` + root `AGENTS.md`. Scheduled for deletion once the pipeline is verified (Phase 6). > Manifest: `docs/archive/2026-07-ai-artifacts/MANIFEST.md` --- name: 02-persist description: Persists the classifier's JSON output to the pipeline state and marks phase 2 complete. kind: leaf executor: script model: claude-haiku-4-5-20251001 --- # Persist classification Reads the decide step's JSON output, calls `pipeline.py classi
$ install --global
skillsauthnpx skillsauth add neohaskell/neohaskell docs/archive/2026-07-ai-artifacts/claude-skills/integration-pipeline-preview/02-classify-integration/02-persistInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jul 8, 2026, 7:47 AM200.2s1 file scanned
SKILL.md
ARCHIVAL KNOWLEDGE — DO NOT USE OR REFERENCE. Superseded by
codemap/+ rootAGENTS.md. Scheduled for deletion once the pipeline is verified (Phase 6). Manifest:docs/archive/2026-07-ai-artifacts/MANIFEST.md
name: 02-persist description: Persists the classifier's JSON output to the pipeline state and marks phase 2 complete. kind: leaf executor: script model: claude-haiku-4-5-20251001
Persist classification
Reads the decide step's JSON output, calls pipeline.py classify <tier> "<rationale>", then pipeline.py complete 2. The script does not interpret the classifier's decision — it only persists it.
Inputs
decide_output— the JSON document on stdout from../01-decide/. Must parse to an object with at leasttier(one oftrivial,simple,moderate,complex,security-critical) andrationale(string).
Plan
- Parse the JSON → verify:
tierandrationaleare present,tieris one of the five valid values. - Run
pipeline.py classify "$tier" "$rationale"→ verify: exit 0;.integration-pipeline/classification.jsonexists with the tier. - Run
pipeline.py complete 2→ verify:pipeline.py statusshows phase 2 done.
Assumptions:
- The decide step produced exactly one JSON document with no preamble.
- The pipeline has been initialised (phase 1 complete).
If any assumption fails, refuse — do not invent a tier.
Steps
- Extract
tierandrationalefrom the decide step's JSON. Usejq -er '.tier'andjq -er '.rationale'so missing ornullfields exit non-zero with the parser error on stderr. - Invoke
python3 .claude/skills/integration-pipeline-preview/scripts/pipeline.py classify "$tier" "$rationale". Surface stderr on non-zero exit. - Invoke
python3 .claude/skills/integration-pipeline-preview/scripts/pipeline.py complete 2. Surface stderr on non-zero exit.
Output
.integration-pipeline/classification.jsonexists with keystier,rationale,classified_at.- Phase 2 marked complete; the pipeline is ready for phase 3.
Refusals
- JSON does not parse → refuse with the parser error.
tieris not one of the five valid values → refuse and name the invalid value; do not coerce.pipeline.py classifyexits non-zero → surface stderr; do not retry with a different tier.
Related Skills
neohaskell/docs/archive/2026-07-ai-artifacts/claude-skills/neohaskell-style-guide
development
VerifiedTrustedCommunity
> **ARCHIVAL KNOWLEDGE — DO NOT USE OR REFERENCE.** > Superseded by `codemap/` + root `AGENTS.md`. Scheduled for deletion once the pipeline is verified (Phase 6). > Manifest: `docs/archive/2026-07-ai-artifacts/MANIFEST.md` --- name: neohaskell-style-guide description: NeoHaskell coding style reference and enforcement rules. Load when writing, reviewing, or modifying any Haskell code in the NeoHaskell project. Triggers on 'NeoHaskell style', 'NeoHaskell conventions', 'how to write NeoHaskell', '
347SKILL.mdUpdated Jul 9, 2026
neohaskell/docs/archive/2026-07-ai-artifacts/claude-skills/neohaskell-security-review
development
VerifiedTrustedCommunity
> **ARCHIVAL KNOWLEDGE — DO NOT USE OR REFERENCE.** > Superseded by `codemap/` + root `AGENTS.md`. Scheduled for deletion once the pipeline is verified (Phase 6). > Manifest: `docs/archive/2026-07-ai-artifacts/MANIFEST.md` --- name: neohaskell-security-review description: Security & Code Quality review for NeoHaskell. Use when reviewing code changes, PRs, or architectural decisions for security implications. Evaluates OWASP, NIST, EU compliance. Handles pipeline phases 2 (ADR review) and 10 (im
347SKILL.mdUpdated Jul 9, 2026
neohaskell/docs/archive/2026-07-ai-artifacts/claude-skills/neohaskell-qa-designer
development
VerifiedTrustedCommunity
> **ARCHIVAL KNOWLEDGE — DO NOT USE OR REFERENCE.** > Superseded by `codemap/` + root `AGENTS.md`. Scheduled for deletion once the pipeline is verified (Phase 6). > Manifest: `docs/archive/2026-07-ai-artifacts/MANIFEST.md` --- name: neohaskell-qa-designer description: Testing QA Designer for NeoHaskell. Designs comprehensive test specifications with exhaustive edge cases, boundary conditions, and happy paths BEFORE implementation. Handles pipeline phase 6 (Test Spec Design). Outside-in TDD meth
347SKILL.mdUpdated Jul 9, 2026
neohaskell/docs/archive/2026-07-ai-artifacts/claude-skills/neohaskell-performance-review
development
VerifiedTrustedCommunity
> **ARCHIVAL KNOWLEDGE — DO NOT USE OR REFERENCE.** > Superseded by `codemap/` + root `AGENTS.md`. Scheduled for deletion once the pipeline is verified (Phase 6). > Manifest: `docs/archive/2026-07-ai-artifacts/MANIFEST.md` --- name: neohaskell-performance-review description: Performance review for NeoHaskell targeting 50k req/s throughput. Use when reviewing code for performance implications, INLINE pragmas, strictness, and allocation patterns. Handles pipeline phases 3 (ADR review) and 11 (imp
347SKILL.mdUpdated Jul 9, 2026